# zai-org/GLM-4.5

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Repository: https://github.com/zai-org/GLM-4.5
Canonical: https://ross.abutalabs.com/products/glm-45
Homepage: https://z.ai/blog/glm-4.5
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, llm, moe, reasoning-language-models, glm
Last push: 2026-02-01T08:28:10+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 65, release rhythm 35, longevity 29
- inputs: {"age_days": 409, "days_push": 213, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4416, forks 472 (observed 2026-08-28T04:08:48.672369+00:00)

## What it is
GLM-4.5 (and successors GLM-4.6/4.7) is a family of open-weight Mixture-of-Experts foundation models from Z.ai focused on agentic tasks, reasoning, and coding. The repository provides model weights, inference code, and tooling for running the models locally or via API.

## Use cases
- run an open-source LLM for agentic coding tasks
- self-host a reasoning model for chat and tool use
- integrate an LLM into coding agents like Claude Code or Cline
- evaluate open-weight models on SWE-bench and reasoning benchmarks
- fine-tune or build applications on a MoE foundation model

## When to choose
- you need an open-weight LLM strong at coding, reasoning, and tool calling
- you want to self-host a capable agentic model on your own GPU infrastructure
- you need a model that works with mainstream agent frameworks

## When to avoid
- you need a small model for edge or CPU-only deployment
- you only need a hosted API without managing weights and GPUs
- your workload is specialized outside coding, reasoning, and agentic use

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, agent-framework, machine-learning, llm-training
- domain: large-language-models, artificial-intelligence, deep-learning
- platform: python
- tags: moe, foundation-model, reasoning, coding-llm, open-weights, glm, agentic-ai, ai-agents, gpu, linux, docker

## Member repositories
- zai-org/GLM-4.5 (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:48.672369+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:21:00.925868+00:00, confidence not recorded.
  - readme: https://github.com/zai-org/GLM-4.5 (fetched 2026-08-28T04:08:48.672369+00:00, sha da6efc6b6c8f)
  - homepage: https://z.ai/blog/glm-4.5 (fetched 2026-08-29T09:08:43.837742+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.